UWB and V2X-based vehicle-road cooperation warning method and device, and electronic equipment

Abstract

This invention discloses a vehicle-road cooperative early warning method, device, and electronic equipment based on UWB and V2X, comprising: acquiring vehicle driving status data of a target area via roadside equipment using V2X communication, and acquiring UWB positioning data of other road participants in the target area based on UWB ranging; constructing road participant graph structure data of the target area based on the driving status data and UWB positioning data; inputting the road participant graph structure data into a pre-trained road collision risk prediction model to obtain road collision risk values ​​for vehicles and other road participants; and issuing early warnings to vehicles and other road participants based on the road collision risk values. This invention improves the accuracy and comprehensiveness of vehicle-road cooperative early warning, ensures road traffic safety, and can be applied to the field of intelligent transportation technology.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a vehicle-road cooperative early warning method, device, and electronic device based on UWB and V2X. Background Technology

[0002] Vehicle-road cooperative early warning is one of the core functions of intelligent transportation systems. It relies on technologies such as vehicle-to-everything (V2X), the Internet of Things (IoT), and big data to realize information interaction between vehicles and road facilities, between vehicles, and between vehicles and cloud platforms, so as to detect road risks in advance and issue early warnings, thereby avoiding or reducing traffic accidents.

[0003] Current vehicle-road cooperative early warning technologies have the following shortcomings: traditional V2X has insufficient positioning accuracy for vulnerable traffic participants such as pedestrians and non-motorized vehicles; many solutions only provide single early warnings on the vehicle side without linking to push proximity reminders to pedestrians; the accuracy of early warnings is limited by the scenario, making it difficult to cope with the diverse risks at complex intersections, easily leading to collision accidents, and failing to meet the needs of comprehensive safety protection.

[0004] The above problems urgently need to be addressed. Summary of the Invention

[0005] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0006] Therefore, one objective of this invention is to provide a vehicle-road cooperative early warning method based on UWB and V2X. This method acquires vehicle driving status data based on V2X communication, acquires UWB positioning data of other road participants based on UWB ranging, constructs road participant graph structure data based on driving status data and UWB positioning data, and predicts road collision risk values ​​of vehicles and other road participants by combining them with a pre-trained road collision risk prediction model. Thus, early warnings can be issued to vehicles and other road participants based on the road collision risk values, improving the accuracy and comprehensiveness of vehicle-road cooperative early warning and ensuring road traffic safety.

[0007] Another objective of this invention is to provide a vehicle-road cooperative early warning device based on UWB and V2X.

[0008] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a vehicle-road cooperative early warning method based on UWB and V2X, comprising the following steps: The driving status data of vehicles in the target area is obtained through roadside equipment based on V2X communication, and the UWB positioning data of other road participants in the target area is obtained based on UWB ranging. Based on the driving status data and the UWB positioning data, construct the road participant map structure data of the target area; The road participant graph structure data is input into a pre-trained road collision risk prediction model to obtain the road collision risk values ​​of the vehicle and the other road participants. Warnings are issued to the vehicle and other road users based on the road collision risk value.

[0009] Furthermore, in one embodiment of the present invention, the step of acquiring UWB positioning data of other road participants in the target area based on UWB ranging specifically includes: The roadside equipment sends UWB ranging segments to the UWB devices carried by other road participants at a preset ranging segment transmission frequency, and obtains the ranging segment response returned by the UWB devices. The ranging response data for the corresponding ranging time period is obtained by accumulating energy in the ranging segment response according to the preset energy accumulation window size; Based on the ranging response data, the UWB positioning distance between the UWB device and the roadside device, as well as the azimuth angle of the UWB device relative to the roadside device, are calculated using the time-of-flight algorithm and the angle-of-arrival ranging algorithm. The corresponding UWB positioning data of the other road participants is generated based on the UWB positioning distance and the azimuth angle.

[0010] Furthermore, in one embodiment of the present invention, the step of constructing the road participant map structure data of the target area based on the driving status data and the UWB positioning data specifically includes: The vehicle and other road participants are taken as road participant nodes, and the node characteristics of each road participant node are determined based on the driving status data and the UWB positioning data. The node distance between any two road participant nodes is determined based on the driving status data and the UWB positioning data, and two road participant nodes whose node distance is less than or equal to a preset distance threshold are regarded as adjacent nodes. Construct spatial association edges corresponding to the adjacent nodes, and determine the edge features of the spatial association edges based on the road topology information of the target area; An initial graph structure is constructed using the road participant nodes as vertices and the spatially associated edges as edges. The vertices and edges of the initial graph structure are assigned values ​​based on the node features and edge features respectively, to obtain the road participant graph structure data.

[0011] Furthermore, in one embodiment of the present invention, the node features of the road participant corresponding to the vehicle include real-time location, driving speed, acceleration, driving intention, and vehicle type, and the node features of the road participant nodes corresponding to the other road participants include real-time location, moving speed, moving direction, and road participant type.

[0012] Furthermore, in one embodiment of the present invention, the road collision risk prediction model is trained through the following steps: Obtain driving status samples of test vehicles and UWB positioning samples of other test road participants in the test scenario; Based on the driving status sample and the UWB positioning sample, a road participant graph structure sample is determined, and the road collision risk label corresponding to each sample road participant node in the road participant graph structure sample is determined by manual annotation. The road participant graph structure samples are input into a pre-constructed graph convolutional neural network to obtain the road collision risk prediction value of each sample road participant node; The loss value is determined based on the predicted road collision risk value and the road collision risk label; The parameters of the graph convolutional neural network are updated based on the loss value to obtain the trained road collision risk prediction model.

[0013] Furthermore, in one embodiment of the present invention, the graph convolutional neural network includes an input layer, a graph convolutional layer, a pooling layer, and an output layer. The step of inputting the road participant graph structure samples into the pre-constructed graph convolutional neural network to obtain the road collision risk prediction value for each sample road participant node specifically includes: The road participant graph structure sample is input into the graph convolutional layer through the input layer; The graph convolutional layer is used to perform feature aggregation on the road participant graph structure samples to obtain the node aggregation features of each road participant node in the samples; The pooling layer compresses the node aggregated features into a node feature vector of a preset length through global mean pooling. The output layer maps the node feature vectors to the road collision risk prediction values ​​corresponding to the sample road participant nodes.

[0014] Furthermore, in one embodiment of the present invention, the step of issuing warnings to the vehicle and other road users based on the road collision risk value specifically includes: The corresponding first warning level is determined based on the road collision risk value of the vehicle, and the corresponding first warning content is issued to the vehicle through the roadside equipment according to the first warning level; The corresponding second warning level is determined based on the road collision risk value of the other road participants, and the corresponding second warning content is pushed to the UWB devices carried by the other road participants through the roadside equipment according to the second warning level.

[0015] On the other hand, embodiments of the present invention provide a vehicle-road cooperative early warning device based on UWB and V2X, comprising: The data acquisition module is used to acquire vehicle driving status data in the target area through roadside equipment based on V2X communication, and to acquire UWB positioning data of other road participants in the target area based on UWB ranging. The graph structure data construction module is used to construct the road participant graph structure data of the target area based on the driving status data and the UWB positioning data. The road collision risk prediction module is used to input the road participant graph structure data into a pre-trained road collision risk prediction model to obtain the road collision risk values ​​of the vehicle and the other road participants. The early warning module is used to issue warnings to the vehicle and other road users based on the road collision risk value.

[0016] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described vehicle-road cooperative early warning method based on UWB and V2X.

[0017] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described vehicle-road cooperative early warning method based on UWB and V2X.

[0018] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described vehicle-road cooperative early warning method based on UWB and V2X.

[0019] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention, through roadside equipment, acquires vehicle driving status data of a target area via V2X communication and obtains UWB positioning data of other road users in the target area via UWB ranging. Based on the driving status data and UWB positioning data, a road user graph structure data of the target area is constructed. This road user graph structure data is then input into a pre-trained road collision risk prediction model to obtain road collision risk values ​​for vehicles and other road users. Warnings are then issued to vehicles and other road users based on these road collision risk values. This invention, by acquiring vehicle driving status data via V2X communication and obtaining UWB positioning data of other road users via UWB ranging, constructing a road user graph structure data based on the driving status data and UWB positioning data, and combining this with a pre-trained road collision risk prediction model to predict road collision risk values ​​for vehicles and other road users, improves the accuracy and comprehensiveness of vehicle-road cooperative warnings and ensures road traffic safety. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of a vehicle-road cooperative early warning method based on UWB and V2X provided in this embodiment of the invention; Figure 2 This is a structural block diagram of a vehicle-road cooperative early warning device based on UWB and V2X provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0024] The vehicle-road cooperative early warning method based on UWB and V2X provided in this invention can be applied to terminals, servers, or software running on either terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the vehicle-road cooperative early warning method based on UWB and V2X, but is not limited to the above forms.

[0025] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user parking space location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0027] Reference Figure 1 This invention provides a vehicle-road cooperative early warning method based on UWB and V2X, specifically including the following steps: S101. Obtain vehicle driving status data in the target area through roadside equipment based on V2X communication, and obtain UWB positioning data of other road participants in the target area based on UWB ranging. S102. Construct a road participant map structure data for the target area based on driving status data and UWB positioning data; S103. Input the road participant graph structure data into the pre-trained road collision risk prediction model to obtain the road collision risk values ​​of vehicles and other road participants; S104. Provide warnings to vehicles and other road users based on road collision risk values.

[0028] Specifically, in this embodiment of the invention, UWB devices are used as mobile sensing nodes to accurately locate the positions of pedestrians, non-motorized vehicles, and other road users, and output UWB positioning data. Vehicle driving status data is acquired based on V2X communication, and the UWB positioning data and driving status data are fused through roadside equipment to generate road user graph structure data. Based on a pre-trained road collision risk prediction model and this road user graph structure data, the road collision risk values ​​of vehicles and other road users are accurately predicted. According to the road collision risk values, graded warnings such as alerts, deceleration, and emergency braking are issued to vehicles. Simultaneously, vehicle approach warnings are pushed to pedestrians / non-motorized vehicles through UWB devices, thereby preventing traffic collisions.

[0029] This invention acquires vehicle driving status data based on V2X communication and obtains UWB positioning data of other road users based on UWB ranging. A road user graph structure is constructed based on the driving status data and UWB positioning data. Combined with a pre-trained road collision risk prediction model, road collision risk values ​​for vehicles and other road users are predicted. This allows for early warnings to be issued to vehicles and other road users based on these risk values, improving the accuracy and comprehensiveness of vehicle-road cooperative early warning and ensuring road traffic safety. It can be recognized that this invention achieves "vehicle-road-pedestrian" three-way cooperative early warning by integrating V2X communication and UWB ranging, improving traffic safety in complex scenarios such as right turns at intersections and unsignalized intersections.

[0030] As a further optional implementation, UWB positioning data of other road users in the target area is acquired based on UWB ranging, specifically including: S1011. The roadside equipment sends UWB ranging segments to the UWB devices carried by other road users according to the preset ranging segment transmission frequency, and obtains the ranging segment response returned by the UWB devices. S1012. Accumulate the energy of the ranging segment response according to the preset energy accumulation window size to obtain the ranging response data for the corresponding ranging time period; S1013. Calculate the UWB positioning distance between the UWB device and the roadside device, as well as the azimuth angle of the UWB device relative to the roadside device, based on the ranging response data, using the time-of-flight algorithm and the angle-of-arrival ranging algorithm. S1014. Generate corresponding UWB positioning data for other road participants based on UWB positioning distance and azimuth.

[0031] Specifically, roadside equipment continuously sends narrow-pulse UWB ranging segments to UWB devices carried by other road users according to a preset ranging segment transmission frequency. After receiving the ranging segments, the UWB devices immediately return ranging segment responses containing timestamps. The roadside equipment continuously receives and records these response signals. Based on preset energy accumulation window parameters, the roadside equipment accumulates the energy of multiple sets of ranging segment responses received within the same time period to enhance the effective signal strength and reduce noise interference, thereby obtaining ranging response data. Subsequently, the precise distance between the UWB devices and the roadside equipment is calculated using a time-of-flight (ToF) algorithm combined with the propagation speed of the UWB signal. In addition, by combining the ranging response data from multiple roadside devices, the azimuth angle of the UWB devices can be obtained through an angle of arrival (AoA) ranging algorithm, and finally, the UWB positioning data is obtained.

[0032] As a further optional implementation, road participant map structure data for the target area is constructed based on driving status data and UWB positioning data, specifically including: S1021. Treat vehicles and other road participants as road participant nodes, and determine the node characteristics of each road participant node based on driving status data and UWB positioning data. S1022. Determine the node distance between any two road participant nodes based on driving status data and UWB positioning data, and designate two road participant nodes whose node distance is less than or equal to a preset distance threshold as adjacent nodes. S1023. Construct spatial association edges corresponding to adjacent nodes, and determine the edge characteristics of the spatial association edges based on the road topology information of the target area. S1024. Construct the initial graph structure using road participant nodes as vertices and spatially related edges as edges. S1025. Assign values ​​to the vertices and edges of the initial graph structure according to the node features and edge features respectively to obtain the road participant graph structure data.

[0033] As an optional implementation, the node characteristics of the road participant corresponding to the vehicle include real-time location, driving speed, acceleration, driving intention, and vehicle type, while the node characteristics of the road participant nodes corresponding to other road participants include real-time location, movement speed, movement direction, and road participant type.

[0034] Specifically, vehicles and other road participants are treated as road participant nodes. The node characteristics of each road participant node are determined based on driving status data and UWB positioning data. For vehicles, a multi-dimensional feature vector of the corresponding node is formed based on real-time location, driving speed, acceleration, driving intention, and vehicle type. For other road participant nodes, a multi-dimensional feature vector of the corresponding node is formed based on real-time location, moving speed, moving direction, and road participant type.

[0035] The distance between any two road participant nodes is determined based on driving status data and UWB positioning data. Two road participant nodes whose distance is less than or equal to a preset distance threshold are considered as adjacent nodes. For example, when the distance between two nodes is less than or equal to 50 meters, the corresponding two nodes are considered as adjacent nodes.

[0036] Construct spatially related edges corresponding to adjacent nodes, and determine the edge features of the spatially related edges based on the road topology information of the target area. Specifically, based on the road topology information, information such as road structure, road surface condition parameters, and traffic facilities between the corresponding locations of adjacent nodes can be determined, thereby obtaining the edge features.

[0037] Using road participant nodes as vertices and spatial connection edges between adjacent nodes as edges, the node feature vectors and edge feature vectors are assigned to the corresponding vertices and edges respectively, ultimately forming a heterogeneous graph structure data containing N nodes and M edges, which is the road participant graph structure data.

[0038] As an optional implementation, the road collision risk prediction model is trained through the following steps: S201. Obtain driving status samples of the test vehicle and UWB positioning samples of other test road participants in the test scenario; S202. Determine the road participant graph structure sample based on the driving status sample and the UWB positioning sample, and determine the road collision risk label corresponding to each road participant node in the road participant graph structure sample through manual annotation. S203. Input the road participant graph structure samples into a pre-built graph convolutional neural network to obtain the road collision risk prediction value of each sample road participant node; S204. Determine the loss value based on the predicted road collision risk value and the road collision risk label; S205. Update the parameters of the graph convolutional neural network based on the loss value to obtain the trained road collision risk prediction model.

[0039] Specifically, the process involves acquiring driving state samples of the test vehicle and UWB positioning samples of other road participants in the test scenario; determining road participant graph structure samples based on the driving state samples and UWB positioning samples, and manually labeling each road participant node in the road participant graph structure samples to determine the road collision risk label; inputting the road participant graph structure samples into a pre-built graph convolutional neural network to obtain the predicted road collision risk value for each road participant node; determining the loss value based on the predicted road collision risk value and the road collision risk label; updating the parameters of the graph convolutional neural network based on the loss value to complete one iteration of training; stopping training when the number of iterations reaches a preset threshold, or when the loss value exceeds the preset threshold, to obtain the trained road collision risk prediction model.

[0040] As a further optional implementation, the graph convolutional neural network includes an input layer, a graph convolutional layer, a pooling layer, and an output layer. Road participant graph structure samples are input into the pre-constructed graph convolutional neural network to obtain the road collision risk prediction value for each sample road participant node. Specifically, this includes: S2031. Input the road participant graph structure sample into the graph convolutional layer through the input layer; S2032. The feature aggregation of the road participant graph structure samples is performed through graph convolutional layers to obtain the node aggregation features of each sample road participant node. S2033. The node aggregate features are compressed into a node feature vector of a preset length through global mean pooling using a pooling layer. S2034. The output layer maps the node feature vectors to the road collision risk prediction values ​​of the corresponding sample road participant nodes.

[0041] Specifically, in this embodiment of the invention, a graph convolutional neural network (GAT) based on an attention mechanism is used to train the road collision risk prediction model. The graph convolutional neural network includes: Input layer: Used to receive the node feature matrix and edge feature matrix of graph structure data; Graph Convolutional Layers: Three graph convolutional layers are set up, each containing 64 hidden units. An attention mechanism is used to aggregate features and learn the dependencies between nodes. Pooling layer: Global mean pooling is used to compress the aggregated features of nodes into a fixed-length feature vector; Output layer: The Softmax function maps the node feature vectors to the road collision risk prediction values ​​of the corresponding sample nodes.

[0042] The training process for the road collision risk prediction model is as follows: Dataset construction: Obtain driving status samples of test vehicles and UWB positioning samples of other test road participants in the test scenario; determine road participant graph structure samples based on driving status samples and UWB positioning samples, and determine the road collision risk label corresponding to each road participant node in the road participant graph structure samples through manual annotation; finally, divide it into training set, validation set and test set in a 7:2:1 ratio. Define the loss function: Use the cross-entropy loss function, combined with L2 regularization to prevent overfitting; Configure the optimizer: Select the Adam optimizer, set the initial learning rate to 0.001, and use a learning rate decay strategy; Iterative update: The training is conducted in 50 rounds. After each round of training, the model performance is evaluated on the validation set. Training is terminated early when the accuracy on the validation set does not improve for 5 consecutive rounds.

[0043] By inputting the real-time constructed road participant graph structure data of the target area into the trained road collision risk prediction model, the road collision risk value of each vehicle and other road participants in the target area can be output. Finally, warnings can be issued to vehicles and other road participants based on the road collision risk value.

[0044] As a further optional implementation, warnings are issued to vehicles and other road users based on road collision risk values, specifically including: S1041. Determine the corresponding first warning level based on the road collision risk value of the vehicle, and issue the corresponding first warning content to the vehicle through the roadside equipment according to the first warning level; S1042. Determine the corresponding second warning level based on the road collision risk value of other road participants, and push the corresponding second warning content to the UWB devices carried by other road participants through the roadside equipment according to the second warning level.

[0045] Specifically, a first warning level is determined based on the road collision risk value of the vehicle, and the roadside equipment issues graded warnings such as prompts, deceleration, and emergency braking to the vehicle according to the first warning level; a second warning level is determined based on the road collision risk value of pedestrians / non-motorized vehicles, and the roadside equipment pushes vehicle approach warnings to the UWB devices of pedestrians / non-motorized vehicles. The warning method can also be adjusted according to the second warning level, including text display, voice broadcast, sound and light warning, etc., which will not be described in detail in this embodiment of the invention.

[0046] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention acquire vehicle driving status data based on V2X communication, acquire UWB positioning data of other road participants based on UWB ranging, construct road participant graph structure data based on the driving status data and UWB positioning data, and combine this with a pre-trained road collision risk prediction model to predict the road collision risk value of vehicles and other road participants. Therefore, warnings can be issued to vehicles and other road participants based on these road collision risk values, improving the accuracy and comprehensiveness of vehicle-road cooperative warnings and ensuring road traffic safety.

[0047] Reference Figure 2 This invention provides a vehicle-road cooperative early warning device based on UWB and V2X, comprising: The data acquisition module is used to acquire the driving status data of vehicles in the target area through roadside equipment based on V2X communication, and to acquire the UWB positioning data of other road participants in the target area based on UWB ranging. The graph structure data construction module is used to construct the road participant graph structure data of the target area based on driving status data and UWB positioning data. The road collision risk prediction module is used to input road participant graph structure data into a pre-trained road collision risk prediction model to obtain road collision risk values ​​for vehicles and other road participants. The warning module is used to issue warnings to vehicles and other road users based on road collision risk values.

[0048] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0049] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned vehicle-road cooperative early warning method based on UWB and V2X.

[0050] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0051] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the aforementioned UWB and V2X-based vehicle-road cooperative early warning method.

[0052] This invention provides a computer-readable storage medium that can execute a vehicle-road cooperative early warning method based on UWB and V2X provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0053] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned vehicle-road cooperative early warning method based on UWB and V2X.

[0054] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0055] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0056] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0057] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0058] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0059] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0060] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0062] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0063] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0064] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0065] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0066] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A vehicle-road cooperative early warning method based on UWB and V2X, characterized in that, Includes the following steps: The driving status data of vehicles in the target area is obtained through roadside equipment based on V2X communication, and the UWB positioning data of other road participants in the target area is obtained based on UWB ranging. Based on the driving status data and the UWB positioning data, construct the road participant map structure data of the target area; The road participant graph structure data is input into a pre-trained road collision risk prediction model to obtain the road collision risk values ​​of the vehicle and the other road participants. Warnings are issued to the vehicle and other road users based on the road collision risk value.

2. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 1, characterized in that, The acquisition of UWB positioning data of other road participants in the target area based on UWB ranging specifically includes: The roadside equipment sends UWB ranging segments to the UWB devices carried by other road participants at a preset ranging segment transmission frequency, and obtains the ranging segment response returned by the UWB devices. The ranging response data for the corresponding ranging time period is obtained by accumulating energy in the ranging segment response according to the preset energy accumulation window size; Based on the ranging response data, the UWB positioning distance between the UWB device and the roadside device, as well as the azimuth angle of the UWB device relative to the roadside device, are calculated using the time-of-flight algorithm and the angle-of-arrival ranging algorithm. The corresponding UWB positioning data of the other road participants is generated based on the UWB positioning distance and the azimuth angle.

3. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 1, characterized in that, The step of constructing the road participant map structure data for the target area based on the driving status data and the UWB positioning data specifically includes: The vehicle and other road participants are taken as road participant nodes, and the node characteristics of each road participant node are determined based on the driving status data and the UWB positioning data. The node distance between any two road participant nodes is determined based on the driving status data and the UWB positioning data, and two road participant nodes whose node distance is less than or equal to a preset distance threshold are regarded as adjacent nodes. Construct spatial association edges corresponding to the adjacent nodes, and determine the edge features of the spatial association edges based on the road topology information of the target area; An initial graph structure is constructed using the road participant nodes as vertices and the spatially associated edges as edges. The vertices and edges of the initial graph structure are assigned values ​​based on the node features and edge features respectively, to obtain the road participant graph structure data.

4. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 3, characterized in that, The node characteristics of the road participant corresponding to the vehicle include real-time location, driving speed, acceleration, driving intention, and vehicle type; the node characteristics of the road participant nodes corresponding to the other road participants include real-time location, moving speed, moving direction, and road participant type.

5. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 1, characterized in that, The road collision risk prediction model is trained through the following steps: Obtain driving status samples of test vehicles and UWB positioning samples of other test road participants in the test scenario; Based on the driving status sample and the UWB positioning sample, a road participant graph structure sample is determined, and the road collision risk label corresponding to each sample road participant node in the road participant graph structure sample is determined by manual annotation. The road participant graph structure samples are input into a pre-constructed graph convolutional neural network to obtain the road collision risk prediction value of each sample road participant node; The loss value is determined based on the predicted road collision risk value and the road collision risk label; The parameters of the graph convolutional neural network are updated based on the loss value to obtain the trained road collision risk prediction model.

6. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 5, characterized in that, The graph convolutional neural network includes an input layer, a graph convolutional layer, a pooling layer, and an output layer. The step of inputting the road participant graph structure samples into the pre-constructed graph convolutional neural network to obtain the road collision risk prediction value for each sample road participant node specifically includes: The road participant graph structure sample is input into the graph convolutional layer through the input layer; The graph convolutional layer is used to perform feature aggregation on the road participant graph structure samples to obtain the node aggregation features of each road participant node in the samples; The pooling layer compresses the node aggregated features into a node feature vector of a preset length through global mean pooling. The output layer maps the node feature vectors to the road collision risk prediction values ​​corresponding to the sample road participant nodes.

7. The vehicle-road cooperative early warning method based on UWB and V2X according to claim 2, characterized in that, The method of issuing warnings to the vehicle and other road users based on the road collision risk value specifically includes: The corresponding first warning level is determined based on the road collision risk value of the vehicle, and the corresponding first warning content is issued to the vehicle through the roadside equipment according to the first warning level; The corresponding second warning level is determined based on the road collision risk value of the other road participants, and the corresponding second warning content is pushed to the UWB devices carried by the other road participants through the roadside equipment according to the second warning level.

8. A vehicle-road cooperative early warning device based on UWB and V2X, characterized in that, include: The data acquisition module is used to acquire the driving status data of vehicles in the target area through roadside equipment based on V2X communication, and to acquire the UWB positioning data of other road participants in the target area based on UWB ranging. The graph structure data construction module is used to construct the road participant graph structure data of the target area based on the driving status data and the UWB positioning data. The road collision risk prediction module is used to input the road participant graph structure data into a pre-trained road collision risk prediction model to obtain the road collision risk values ​​of the vehicle and the other road participants. The early warning module is used to issue warnings to the vehicle and other road users based on the road collision risk value.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a vehicle-road cooperative early warning method based on UWB and V2X as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a vehicle-road cooperative early warning method based on UWB and V2X as described in any one of claims 1 to 7.

Images